A real-time bird sound recognition system using a low-cost microcontroller

Okan Küc̣üktopcu, Engin Masazade, Cem Ünsalan, Pramod Kumar Varshney

Research output: Contribution to journalArticle

Abstract

Monitoring the environment using stand-alone sensor nodes provides valuable information to researchers, practitioners and policy makers. One such problem in this area is bird activity monitoring using its sound patterns. There are several existing devices that can record bird sounds in a region. Then, the stored data is processed off-line. However, the time between the acquisition and processing stages while using such devices is generally of the order of weeks. This approach is not amenable to real-time monitoring. Therefore, there is a need for a system which is able to both monitor the environment and process data on the system itself. The most important attribute of such a system is its power consumption since it operates in the environment only by its battery. In this study, we propose such a stand-alone, energy efficient, low-level, custom-made, real-time bird call processing system concentrated on single-labeled bird calls. The system is composed of a microphone, Texas Instruments Tiva C microcontroller, and a storage unit. The proposed system enables data recording, preliminary on-board signal processing, feature extraction, classification, and data storage. In the proposed system, we simultaneously record and process data. Hence, the system not only stores the environmental sounds, it also classifies the detected birds on-site. The proposed system offers flexibility (both in hardware and software) for expansion.

Original languageEnglish (US)
Pages (from-to)194-201
Number of pages8
JournalApplied Acoustics
Volume148
DOIs
StatePublished - May 1 2019

Fingerprint

birds
acoustics
data recording
data storage
microphones
pattern recognition
electric batteries
signal processing
acquisition
flexibility
hardware
computer programs
expansion
sensors

Keywords

  • Bird call processing
  • Feature extraction
  • Mel frequency cepstrum coefficients
  • Real-time processing
  • Spectral noise gating

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

A real-time bird sound recognition system using a low-cost microcontroller. / Küc̣üktopcu, Okan; Masazade, Engin; Ünsalan, Cem; Varshney, Pramod Kumar.

In: Applied Acoustics, Vol. 148, 01.05.2019, p. 194-201.

Research output: Contribution to journalArticle

Küc̣üktopcu, Okan ; Masazade, Engin ; Ünsalan, Cem ; Varshney, Pramod Kumar. / A real-time bird sound recognition system using a low-cost microcontroller. In: Applied Acoustics. 2019 ; Vol. 148. pp. 194-201.
@article{289a7a7933a94eccb7751dd17c66cf18,
title = "A real-time bird sound recognition system using a low-cost microcontroller",
abstract = "Monitoring the environment using stand-alone sensor nodes provides valuable information to researchers, practitioners and policy makers. One such problem in this area is bird activity monitoring using its sound patterns. There are several existing devices that can record bird sounds in a region. Then, the stored data is processed off-line. However, the time between the acquisition and processing stages while using such devices is generally of the order of weeks. This approach is not amenable to real-time monitoring. Therefore, there is a need for a system which is able to both monitor the environment and process data on the system itself. The most important attribute of such a system is its power consumption since it operates in the environment only by its battery. In this study, we propose such a stand-alone, energy efficient, low-level, custom-made, real-time bird call processing system concentrated on single-labeled bird calls. The system is composed of a microphone, Texas Instruments Tiva C microcontroller, and a storage unit. The proposed system enables data recording, preliminary on-board signal processing, feature extraction, classification, and data storage. In the proposed system, we simultaneously record and process data. Hence, the system not only stores the environmental sounds, it also classifies the detected birds on-site. The proposed system offers flexibility (both in hardware and software) for expansion.",
keywords = "Bird call processing, Feature extraction, Mel frequency cepstrum coefficients, Real-time processing, Spectral noise gating",
author = "Okan K{\"u}c̣{\"u}ktopcu and Engin Masazade and Cem {\"U}nsalan and Varshney, {Pramod Kumar}",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.apacoust.2018.12.028",
language = "English (US)",
volume = "148",
pages = "194--201",
journal = "Applied Acoustics",
issn = "0003-682X",
publisher = "Elsevier",

}

TY - JOUR

T1 - A real-time bird sound recognition system using a low-cost microcontroller

AU - Küc̣üktopcu, Okan

AU - Masazade, Engin

AU - Ünsalan, Cem

AU - Varshney, Pramod Kumar

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Monitoring the environment using stand-alone sensor nodes provides valuable information to researchers, practitioners and policy makers. One such problem in this area is bird activity monitoring using its sound patterns. There are several existing devices that can record bird sounds in a region. Then, the stored data is processed off-line. However, the time between the acquisition and processing stages while using such devices is generally of the order of weeks. This approach is not amenable to real-time monitoring. Therefore, there is a need for a system which is able to both monitor the environment and process data on the system itself. The most important attribute of such a system is its power consumption since it operates in the environment only by its battery. In this study, we propose such a stand-alone, energy efficient, low-level, custom-made, real-time bird call processing system concentrated on single-labeled bird calls. The system is composed of a microphone, Texas Instruments Tiva C microcontroller, and a storage unit. The proposed system enables data recording, preliminary on-board signal processing, feature extraction, classification, and data storage. In the proposed system, we simultaneously record and process data. Hence, the system not only stores the environmental sounds, it also classifies the detected birds on-site. The proposed system offers flexibility (both in hardware and software) for expansion.

AB - Monitoring the environment using stand-alone sensor nodes provides valuable information to researchers, practitioners and policy makers. One such problem in this area is bird activity monitoring using its sound patterns. There are several existing devices that can record bird sounds in a region. Then, the stored data is processed off-line. However, the time between the acquisition and processing stages while using such devices is generally of the order of weeks. This approach is not amenable to real-time monitoring. Therefore, there is a need for a system which is able to both monitor the environment and process data on the system itself. The most important attribute of such a system is its power consumption since it operates in the environment only by its battery. In this study, we propose such a stand-alone, energy efficient, low-level, custom-made, real-time bird call processing system concentrated on single-labeled bird calls. The system is composed of a microphone, Texas Instruments Tiva C microcontroller, and a storage unit. The proposed system enables data recording, preliminary on-board signal processing, feature extraction, classification, and data storage. In the proposed system, we simultaneously record and process data. Hence, the system not only stores the environmental sounds, it also classifies the detected birds on-site. The proposed system offers flexibility (both in hardware and software) for expansion.

KW - Bird call processing

KW - Feature extraction

KW - Mel frequency cepstrum coefficients

KW - Real-time processing

KW - Spectral noise gating

UR - http://www.scopus.com/inward/record.url?scp=85059192205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059192205&partnerID=8YFLogxK

U2 - 10.1016/j.apacoust.2018.12.028

DO - 10.1016/j.apacoust.2018.12.028

M3 - Article

VL - 148

SP - 194

EP - 201

JO - Applied Acoustics

JF - Applied Acoustics

SN - 0003-682X

ER -